What does Soil Couples, Copper Antennas and Electroculture Trials conclude, in numbers, about “Testing in the Field: Randomised Blocks, Split Plots, Power Analysis and Guard Strips”?

Answer: Chapter 6 treats randomised blocks, split plots and power analysis: testing the main-plot factor against the subplot error raises the false-positive rate to 0.3160, and a rod's influence on the ground-level field falls below one per cent beyond 3.43 metres.

Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; the book is not agronomic or investment advice and judges no brand. Chapter 1 uses the Nernst equation to find an open-circuit voltage of about 1.0734 volts for a copper-zinc couple in an illustrative soil solution and shows that its energy comes from corroding zinc.

中文版

Data table

The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.3160

null true; 4000 simulated trials per row; 2 x 3 split plot
rsd_mainsd_subF crit right/wrongfalse positives
rightwrong
40.080.0410.128 /4.5430.04570.3160
40.050.0510.128 /4.5430.05320.2087
60.080.046.608 /4.2420.05300.3252
80.100.035.591 /4.1210.04850.3430
Show the full program
# Chapter 6. p62: split-plot field trial, rods on main plots and zinc
# rates on subplots; what happens when the rod effect is tested against
# the wrong error term.
# Model: y = block + A + w(main plot) + B + e, r blocks, a = 2 main
# treatments (rod, no rod), b = 3 subplots.  The null is true: no rod
# effect.  Correct test: MS_A / MS(block x A), df 1 and (r-1)(a-1).
# Wrong test: MS_A / pooled subplot residual, as if every subplot were
# an independent plot.  Error SDs (as yield fractions) are
# illustrative; fixed seed.
import math
import random
import statistics


def betacf(a, b, x):
    qab, qap, qam = a + b, a + 1.0, a - 1.0
    c, d = 1.0, 1.0 - qab * x / qap
    d = 1.0 / (d if abs(d) > 1e-300 else 1e-300)
    h = d
    for m in range(1, 300):
        m2 = 2 * m
        for aa in (m * (b - m) * x / ((qam + m2) * (a + m2)),
                   -(a + m) * (qab + m) * x / ((a + m2) * (qap + m2))):
            d = 1.0 + aa * d
            d = 1.0 / (d if abs(d) > 1e-300 else 1e-300)
            c = 1.0 + aa / c
            c = c if abs(c) > 1e-300 else 1e-300
            h *= d * c
        if abs(d * c - 1.0) < 1e-14:
            break
    return h


def betai(a, b, x):
    if x <= 0.0 or x >= 1.0:
        return 0.0 if x <= 0.0 else 1.0
    lb = (math.lgamma(a + b) - math.lgamma(a) - math.lgamma(b)
          + a * math.log(x) + b * math.log(1.0 - x))
    if x < (a + 1.0) / (a + b + 2.0):
        return math.exp(lb) * betacf(a, b, x) / a
    return 1.0 - math.exp(lb) * betacf(b, a, 1.0 - x) / b


def f_crit(d1, d2, alpha=0.05):
    lo, hi = 0.0, 1000.0
    for _ in range(100):
        mid = (lo + hi) / 2.0
        up = betai(d2 / 2.0, d1 / 2.0, d2 / (d2 + d1 * mid))
        lo, hi = (mid, hi) if up > alpha else (lo, mid)
    return (lo + hi) / 2.0


def trial(rng, r, sw, se, a=2, b=3):
    y = [[[0.0] * b for _ in range(a)] for _ in range(r)]
    for i in range(r):
        blk = rng.gauss(0.0, 0.10)
        for j in range(a):
            w = rng.gauss(0.0, sw)
            for k in range(b):
                y[i][j][k] = 1.0 + blk + w + 0.03 * k + rng.gauss(0.0, se)
    g = statistics.fmean(v for i in y for j in i for v in j)
    yi = [statistics.fmean(v for j in y[i] for v in j) for i in range(r)]
    yj = [statistics.fmean(y[i][j][k] for i in range(r) for k in range(b))
          for j in range(a)]
    yk = [statistics.fmean(y[i][j][k] for i in range(r) for j in range(a))
          for k in range(b)]
    yij = [[statistics.fmean(y[i][j]) for j in range(a)] for i in range(r)]
    yjk = [[statistics.fmean(y[i][j][k] for i in range(r))
            for k in range(b)] for j in range(a)]
    ss_tot = math.fsum((v - g) ** 2 for i in y for j in i for v in j)
    ss_r = a * b * math.fsum((v - g) ** 2 for v in yi)
    ss_a = r * b * math.fsum((v - g) ** 2 for v in yj)
    ss_w = b * math.fsum((yij[i][j] - yi[i] - yj[j] + g) ** 2
                         for i in range(r) for j in range(a))
    ss_cells = r * math.fsum((yjk[j][k] - g) ** 2
                             for j in range(a) for k in range(b))
    df_w = (r - 1) * (a - 1)
    df_res = (r - 1) * (a * b - 1)
    ms_a = ss_a
    right = ms_a / (ss_w / df_w)
    wrong = ms_a / ((ss_tot - ss_r - ss_cells) / df_res)
    return right, wrong, df_w, df_res


rng = random.Random(20261112)
print("null true; 4000 simulated trials per row; 2 x 3 split plot")
print(" r   sd_main  sd_sub   F crit right/wrong   false positives")
print("                                          right     wrong")
for r, sw, se in ((4, 0.08, 0.04), (4, 0.05, 0.05), (6, 0.08, 0.04),
                  (8, 0.10, 0.03)):
    fr = fw = 0
    _, _, d1, d2 = trial(rng, r, sw, se)
    cr, cw = f_crit(1, d1), f_crit(1, d2)
    for _ in range(4000):
        a_ok, a_bad, _, _ = trial(rng, r, sw, se)
        fr += a_ok > cr
        fw += a_bad > cw
    fmt = ("{:2d}    {:.2f}    {:.2f}     {:6.3f} / {:6.3f}"
           "     {:.4f}    {:.4f}")
    print(fmt.format(r, sw, se, cr, cw, fr / 4000, fw / 4000))

Single source and citation

Fan, Y. (2026). Nernst Potentials in Soil Electrochemistry, Nanowatt Harvest Limits of Passive Copper Antennas and Field Block Designs for Electroculture Yield Claims (Version 1.0.0), Chapter 6: Testing in the Field: Randomised Blocks, Split Plots, Power Analysis and Guard Strips. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-170 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026170,
  author    = {Fan, Yafu},
  title     = {Nernst Potentials in Soil Electrochemistry, Nanowatt Harvest Limits of Passive Copper Antennas and Field Block Designs for Electroculture Yield Claims},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book